Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to authority and spiritual leadership in a religious context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.67
    ，「
    -0.61
    AccessorTable
    -0.60
     للمعارف
    -0.58
     thy
    -0.57
    fjspx
    -0.56
    :+:
    -0.55
     autorytatywna
    -0.54
    Thy
    -0.53
    thy
    -0.51
    POSITIVE LOGITS
     iſt
    0.82
     juſt
    0.80
     itſelf
    0.78
     ſche
    0.73
     uſed
    0.72
     ſta
    0.72
     becauſe
    0.71
     ſever
    0.71
     uſ
    0.71
     ſch
    0.70
    Act Density 0.037%

    No Known Activations